Summary
In the application of factor analysis to empirical data, a statistical test almost always indicates more factors than researchers expect. However, if one more factor is tried to be extracted, proper solutions cannot be obtained frequently and several problems arise.
This paper investigates causes of the problems and proposes a pragmatic treatment of improper solutions. Further, some recommendations are made on the practical application of factor analysis.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Anderson, J. C. and Gerbing, D. W. (1984). The effect of sampling error on convergence, improper solution, and goodness-of-fit indices for maximum likelihood confirmatory factor analysis,Psychometrika,49, 155–173.
Anderson, T. W. and Rubin, H. (1956). Statistical inference in factor analysis,Proc. Third Berkeley Symp. Math. Statist. Prob.,5, 111–150.
Bechtoldt, H. P. (1961). An empirical study of the factor analysis stability hypothesis,Psychometrika,26, 405–432.
Boomsma, A. (1985). Nonconvergence improper solutions, and starting values in LISREL maximum likelihood estimation,Psychometrika,50, 229–242.
Cattell, R. B. (1965). Factor analysis: an introduction to essentials,Biometrics,21, 190–215.
Driel, O. P. van (1978). On various causes of improper solutions in maximum likelihood factor analysis,Psychometrika,43, 225–243.
Driel, O. P. van, Prins, H. J. and Veltkamp, G. W. (1974). Estimating the parameters of the factor analysis model without the usual constraints of positive definitness,Proceedings of the Symposium on Computational Statistics (COMPSTAT), Vienna, 255–265.
Fukutomi, K. (1973). On the adequacy of factor extraction,TRU Mathematics,9, 119–136.
Geweke, J. F. and Singleton, K. J. (1980). Interpreting the likelihood ratio statistics in factor models when sample size is small,J. Amer. Statist. Ass.,75, 133–137.
Green, B. F. (1952). The orthogonal approximation of an oblique structure in factor analysis,Psychometrika,17, 429–440.
Harman, H. H. (1960).Modern Factor Analysis, University of Chicago Press, Chicago
Harman, H. H. and Fukuda, Y. (1966). Resolution of the Heywood case in the minres solution,Psychometrika,31, 563–571.
Jackson, D. N. and Chan, D. W. (1980). Maximum likelihood estimation in common factor analysis: A causionary note,Psychol. Bull.,88, 502–508.
Jennrich, R. I. and Robinson, S. M. (1969). A Newton-Raphson algorithm for maximum likelihood factor analysis,Psychometrika,34, 111–123.
Jöreskog, K. G. (1967). Some contributions to maximum likelihood factor analysis,Psychometrika,32, 443–482.
Jöreskog, K. G. (1977). Factor analysis by least-squares and maximum-likelihood methods (eds. Enslein, K., Ralston, A. and Wilf, H. S.).Statistical Methods for Digital Computers, Wiley-Interscience, New York, 125–153.
Koopman, R. F. (1978). On Bayesian estimation in unrestricted factor analysis,Psychometrika,43, 109–110.
Lawley, D. N. and Maxwell, A. E. (1971).Factor Analysis as a Statistical Method, 2nd ed., Butterworths, London.
Martin, J. K. and McDonald, R. P. (1975). Bayesian estimation in unrestricted factor analysis: a treatment for Heywood cases,Psychometrika,40, 505–517.
Mattsson, A., Olsson, U. and Rosén, M. (1966). The maximum likelihood method in factor analysis with special consideration to the problem of improper solutions,Research Report, Institute of Statistics, University of Uppsala, Sweden.
Maxwell A. E. (1961). Recent trends in factor analysis,J. R. Statist. Soc., A124, 49–59.
Maxwell, A. E. (1972). Factor analysis: Thomson's sampling theory recalled,Brit. J. Math. Statist. Psychol.,25, 1–21.
Rao, C. R. (1955). Estimation and tests of significance in factor analysis,Psychometrika,20, 93–111.
Rao, C. R. (1965).Linear Statistical Inference and Its Application., Wiley, New York.
Rindskopf, D. (1984). Structural equation models: Empirical identification, Heywood cases, and related problems,Sociol. Meth. Res.,13, 109–119.
Shiba, S. (1972).Factor Analysis (in Japanese), University of Tokyo Press, Tokyo.
Tucker, L. R. and Lewis, C. (1973). A reliability coefficient for maximum likelihood factor analysis,Psychometrika,38, 1–10.
Tumura, Y. and Fukutomi, K. (1968). On the identification in factor analysis,Rep. Statist. Appl. Res.,15, 98–103.
Tumura, Y. and Sato, M. (1980). On the identification in factor analysis,TRU Mathematics,16(2), 121–131.
Tumura, Y. and Sato, M. (1981). On the convergence of iterative procedures in factor analysis,TRU Mathematics,17, 159–168.
Tumura, Y. and Sato, M. (1981). On the convergence of iterative procedures in factor analysis (II),TRU Mathematics,17, 255–271.
Tumura, Y., Fukutomi, K. and Asoo, Y. (1968). On the unique convergence of iterative procedures in factor analysis,TRU Mathematics,4, 52–59.
Author information
Authors and Affiliations
Additional information
This research was supported in part by Grand-in-Aid for Scientific Research of the Ministry of Education, Science and Culture under Contract Number 61730015 and 61530017.
About this article
Cite this article
Sato, M. Pragmatic treatment of improper solutions in factor analysis. Ann Inst Stat Math 39, 443–455 (1987). https://doi.org/10.1007/BF02491481
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF02491481